Attention Feature Map Guided Self-Supervised Monocular Visual Odometry.

Saved in:

Bibliographic Details
Title:	Attention Feature Map Guided Self-Supervised Monocular Visual Odometry.
Authors:	Nan, Bingfei^1,2 nanbf@tdmarco.com
Source:	Journal of Imaging Science & Technology. Nov/Dec2025, Vol. 69 Issue 6, p1-8. 8p.
Subjects:	Visual odometry, Attention, Trajectory measurements, Depth maps (Digital image processing), Machine learning, Measurement errors
Abstract:	This paper presents a self-supervised monocular visual odometry (VO) method guided by attention feature maps, aimed at effectively mitigating the impact of redundant pixels during network training. Existing self-supervised VO methods typically treat all pixels equally when computing photometric error, which can lead to increased sensitivity to noise from irrelevant pixels and, consequently, training errors. To address this issue, the authors adopt a soft-attention mechanism to generate attention feature maps that allow the model to focus on more relevant pixels while downweighting the influence of disruptive ones. This approach enhances the robustness and accuracy of depth estimation and pose tracking. The proposed method achieves competitive results on the KITTI dataset, with Sequences 09 and 10 demonstrating relative rotation errors of 0.022 and 0.032 and relative translation errors of 5.56 and 7.29, respectively. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Imaging Science & Technology is the property of International Society for Imaging Science & Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	This paper presents a self-supervised monocular visual odometry (VO) method guided by attention feature maps, aimed at effectively mitigating the impact of redundant pixels during network training. Existing self-supervised VO methods typically treat all pixels equally when computing photometric error, which can lead to increased sensitivity to noise from irrelevant pixels and, consequently, training errors. To address this issue, the authors adopt a soft-attention mechanism to generate attention feature maps that allow the model to focus on more relevant pixels while downweighting the influence of disruptive ones. This approach enhances the robustness and accuracy of depth estimation and pose tracking. The proposed method achieves competitive results on the KITTI dataset, with Sequences 09 and 10 demonstrating relative rotation errors of 0.022 and 0.032 and relative translation errors of 5.56 and 7.29, respectively. [ABSTRACT FROM AUTHOR]
ISSN:	10623701
DOI:	10.2352/J.ImagingSci.Technol.2025.69.6.060403